JP2013137759A - System and method for generating marketing mix solution - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for generating a marketing mix solution.SOLUTION: The method includes pre-modeling marketing data having a plurality of marketing mix variables. Each of the marketing mix variables is associated with a marketing strategy for one or more products. The method also includes: generating a response model based on the sales and/or income of one or more products for specifying contribution marketing mix variables affecting the sales and/or income of one or more products; and analyzing the response model for searching the contribution of each of the contribution marketing mix variables to the sales and/or income of one or more products.

Description

  The present invention relates generally to marketing and, more particularly, to systems and methods for generating marketing mix solutions.

  Companies spend a lot of money on product marketing. Such expenses are often directed to many different marketing channels such as television advertising, web advertising, newspapers and magazine advertising, among others. It is desirable to evaluate the return on investment (ROI) for the funds spent in marketing activities and generate an optimal marketing mix solution that maximizes product sales / income.

  Typically, a marketing manager needs to perform a thorough and time-consuming analysis by increasing individual marketing elements by one unit to calculate incremental profits from sales. In addition, marketing managers need to optimize marketing budgets and identify efficient marketing activities.

  Unfortunately, analyzing marketing data to determine marketing strategies is extremely complex due to the difficulty in capturing and extracting data from various data sources. In addition, business management often needs to predict future performance of sales / revenue based on changes in marketing strategies, including changes in spending on various marketing channels. In any industry, there are a number of factors that affect corporate performance. Many business organizations generate predictions manually, but they can be very cumbersome and time consuming.

  Therefore, it is desirable to develop techniques for organizing, integrating and analyzing marketing data in order to optimize spending on various marketing channels.

  That is, according to one embodiment of the present invention, a computer-implemented method for generating a marketing mix solution is provided. The method includes pre-modeling marketing data having a plurality of marketing mix variables. Each of these multiple marketing mix variables is associated with a marketing strategy for one or more products. The method also generates a response model based on the sales and / or revenue to identify a contributing marketing mix variable that affects the sales and / or revenue of one or more products, and / or Analyzing a response model to determine an individual contribution of each of the contribution marketing mix variables to the sales and / or revenue of a plurality of products.

  In another embodiment, a system for generating a marketing solution is provided. The system includes a user interface for providing marketing data associated with a marketing strategy for one or more products and a memory circuit configured to store the marketing data. The system also includes a processor configured to access the memory circuit. The processor analyzes the pre-modeled marketing data to pre-model marketing data and using a response model based on sales and / or revenue to determine the sales and / or revenue of one or more products. Configured to identify influencing contributing marketing mix variables.

  In another embodiment, a method for generating a marketing mix solution is provided. The method includes pre-modeling marketing data having a plurality of marketing mix variables. Each of these multiple marketing mix variables is associated with a marketing strategy for one or more products. The method also generates a response model based on the sales and / or revenue to identify a contributing marketing mix variable that affects the sales and / or revenue of one or more products, and / or Analyzing a response model to determine an individual contribution of each of the contribution marketing mix variables to the sales and / or revenue of a plurality of products. The method further includes adjusting one or more marketing strategies in response to each individual contribution of the contributing marketing mix variable.

  These and other features, aspects and advantages of the present invention will become further understood when the following detailed description is read with reference to the accompanying drawings. In the drawings, similar characters represent similar parts throughout the drawings.

1 is a schematic diagram of a system for generating a marketing mix solution according to aspects of the present technique. FIG. FIG. 2 illustrates an exemplary pre-modeling screen of the system of FIG. 1 according to aspects of the present technique. FIG. 6 illustrates another example pre-modeling screen of a system user interface in accordance with aspects of the present technique. FIG. 2 illustrates an exemplary screen for generating a marketing mix variable, such as an adstock variable, using the system of FIG. 1 in accordance with aspects of the present technique. 2 illustrates an exemplary modeling screen of the system of FIG. 1 in accordance with aspects of the present invention. FIG. 2 illustrates an exemplary analysis output screen generated by an analysis module of the system of FIG. 1 in accordance with aspects of the present technique. FIG. 3 illustrates another exemplary analysis output screen generated by the analysis module of the system of FIG. 1 in accordance with aspects of the present technique. FIG. 2 illustrates an exemplary simulation output screen generated by an analysis module of the system of FIG. 1 in accordance with aspects of the present technique. FIG. 6 is a block diagram illustrating an example computing device configured to generate a marketing mix solution, according to aspects of the present technique.

  As will be discussed in detail later, embodiments of the present invention serve to provide a system and method for generating a marketing mix solution. Specifically, according to the present technique, pre-modeling marketing data having various marketing mix variables associated with a marketing strategy for one or more products to generate a response model based on sales and / or revenue. A contributing marketing mix variable that affects sales and / or revenue of one or more products may be identified.

  Furthermore, embodiments of the present invention provide techniques for analyzing response models and determining individual contributions of each contributing marketing mix variable to sales and / or revenue of one or more products. Conveniently, the marketing strategy for one or more products is customized and / or adjusted based on the analysis results to maximize the sales and / or revenue of those products.

  References herein to “one embodiment,” “an embodiment,” and “exemplary embodiment” indicate that the described embodiment can include particular features, structures, or features. All embodiments may not necessarily include that particular mechanism, structure or feature. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular mechanism, structure, or feature is described in connection with certain embodiments, such mechanism, structure, in relation to other embodiments, whether or not explicitly described. Or, implementing the features is considered to be within the knowledge of one skilled in the art.

  Referring now to the drawings and referring first to FIG. 1, a system 10 for generating a marketing mix solution is provided. System 10 includes a user interface 12 for providing marketing data associated with a marketing strategy for one or more products. The marketing data includes a plurality of marketing mix variables, each of the plurality of marketing mix variables being associated with a marketing strategy for one or more products.

  Examples of marketing mix variables include, but are not limited to, sales data for products captured over a period of time, parameters indicating the time / season of the year, and total income of individuals within a selected market area Includes macroeconomic parameters, marketing variables such as the number of product advertisements through various communication channels, and the number of users who visit the website of the store that sells the product. Those skilled in the art will appreciate that a variety of such marketing mix parameters can be envisioned.

  The system 10 further includes a memory circuit 14 for storing marketing data. The memory circuit 14 includes a hard disk drive, an optical drive, a tape drive, a random access memory (RAM), a read only memory (ROM), a programmable read only memory (PROM), and a redundant array of independent disks (RAID). ), Flash memory, magneto-optical memory, holographic memory, bubble memory, magnetic drum, memory stick, Mylar® tape, smart disk, thin film memory, zip drive, and the like.

  In addition, system 10 includes a processor 16 that is configured to access memory circuit 14. The processor 16 pre-models the marketing data and analyzes the pre-modeled marketing data using a response model based on sales and / or revenues to determine the sales and sales of one or more products that will be described in more detail later. Configured to identify contributing marketing mix variables that affect revenue.

  It should be noted that the present invention is not limited to any particular processor for performing the processing tasks of the present invention. As used herein, the term “processor” is intended to represent any machine capable of performing the operations or calculations necessary to perform the tasks of the present invention. The term “processor” is intended to represent any machine that can accept structured input, process the input according to predetermined rules, and generate output.

  Also, as used herein, the phrase “configured as” refers to a combination of hardware and software for a processor to perform the tasks of the present invention, as will be understood by those skilled in the art. Note that it means to have.

  In the illustrated embodiment, the processor 16 includes an application module 18 that is configured to assign each of a plurality of marketing mix variables to one or more marketing mix categories. Marketing mix categories can be predefined by users of the system 10 and can be dynamically updated to add new categories over time. For example, the variables can be divided into categorical variables, continuous variables, and date variables. Variables can be further subdivided into specific marketing mix categories such as, among others, macroeconomic categories, promotional categories, media related categories, seasonal categories.

  The application module 18 is further configured to analyze the marketing mix variables using exploratory data analysis to generate blur modeled marketing data. The user of system 10 can select the type of analysis to be performed. In one exemplary embodiment, univariate analysis can be performed using marketing mix variables. Specifically, a univariate analysis is performed to estimate the value range and frequency for continuous variables. For example, a univariate analysis can be performed to compare product sales / income from various stores.

  In another exemplary embodiment, bivariate analysis can be performed using marketing mix variables. Such bivariate analysis is particularly convenient for analyzing the relationship between any two variables in the data set. For example, a bivariate analysis can be performed to analyze the relationship between product sales from a store and individual store media advertisement ratings.

  In another exemplary embodiment, a time series analysis can be performed to obtain a variable variation pattern over a predetermined observation period. In one exemplary embodiment, a similar time series pattern for two different variables indicates a direct relationship between the two variables. In certain other embodiments, factor analysis can be performed to analyze marketing mix variables.

  The processor 16 further includes an analysis module 20 that is configured to analyze the response model to determine the individual contribution of each contributing marketing mix variable to the sales and / or revenue of one or more products. In one exemplary embodiment, the analysis module 20 is configured to transform and / or add one or more marketing mix variables before generating the sales and / or revenue model. The one or more marketing mix variables can include ad stock variables, event variables, lead variables, and lag variables.

  For example, product marketing strategies typically use product advertisements to promote product sales. Although advertisements have effects that are realized over time, these effects also gradually diminish over a period of time. Typically, new advertisements are added to the existing effects of old advertisements to generate “adstock”. In this exemplary embodiment, ad stock variables corresponding to media variables and promotional variables are created prior to the modeling process. Ad stock variables are ad-stocked at an appropriate decay rate to take into account the carry-over effect of the advertisement. In one embodiment, a broad vent damping effect model is utilized to calculate ad stock for media variables.

  In certain embodiments, mathematical operations on variables can be performed by using transformation functions. For example, new variables can be generated from existing variables using arithmetic transformations using mathematical operators such as logarithm, exponent and square root. In another embodiment, lag / lead conversion can be performed to capture lag or lead effects from media activity and / or macroeconomic variables. In addition, a moving average can be calculated to smooth out short-term fluctuations in the data to determine long-term trends or cycles. In yet another embodiment, an event variable can be created to warn of a specific date and time interval at which the value of the dependent variable is expected to indicate fluctuation / abnormality.

  The analysis module 20 is further configured to generate a response model based on sales and / or revenue and identify contributing marketing mix variables that affect the sales and / or revenue of one or more products. The response model is generated using a linear regression model, a nonlinear regression model, or a mixed model. The variable to be modeled is selected by the system user. For example, the variable may be, among other things, total sales per store or total revenue per store, or sales / income over a period of time.

  In certain embodiments, analysis module 20 provides the user with evaluation criteria related to the performance of the model. For example, statistical evaluation criteria such as R-square, adjusted R-square, p-value, and variance expansion factor (VIF) can be estimated for the model. The analysis module 20 can also generate various statistical plots. For example, a residual plot can be generated to assess the effectiveness of the model.

  The analysis module 20 is further configured to analyze a response model based on sales and / or revenue to identify contributing marketing mix variables that affect the sales and / or revenue of one or more products. In one exemplary embodiment, analysis module 20 is configured to determine the individual contribution of each contributing marketing mix variable to the sales and / or revenue of one or more products. In another exemplary embodiment, expenditures for individual contributions of each contribution marketing mix variable are compared.

  In addition, the individual contribution of each contributing marketing mix variable to the change in sales over a predetermined period is estimated. In yet another embodiment, a return on investment (ROI) is determined for each contributing marketing mix variable. As will be appreciated by those skilled in the art, various plots can be generated to evaluate the above parameters. For example, a pie chart can be generated to compare individual contributions for each marketing mix variable. Similarly, bar charts can be used to compare contributions versus expenditures to assess the cost effectiveness of market strategies used to promote the sale of one or more products.

  Furthermore, the analysis module 20 is configured to generate a marketing mix solution based at least on the individual contributions of each contributing marketing mix variable. In this embodiment, one or more marketing strategies that contribute to the overall sales and / or revenue of one or more products are identified, and spending on the identified marketing strategies is adjusted to generate a marketing mix solution. The In another embodiment, the analysis module 20 is configured to predict sales and / or revenue for one or more products based on a marketing mix solution. Predictive features allow users to compare different scenarios in a product marketing strategy and make any necessary adjustments.

  The processor 16 also includes an optimization module 22 that is configured to generate an optimal marketing mix solution. The optimization module 22 is configured to support multi-layer optimization and can utilize techniques such as genetic algorithms, annealing methods, particle swarm optimization and ant colony optimization. For example, the optimization module 22 can be used to optimize channel spending over various channels over a period of time. In the exemplary embodiment, optimization module 22 is an integral component of system 10. In certain other embodiments, the optimization module 22 may be a separate component that operates in parallel with the main system 10.

  The optimization module 22 can include components such as an input layer, which can be used to provide optimized inputs such as parameters to be optimized along with optimization constraints. In addition, an optimization engine can be used, which includes an optimization algorithm for accessing user-provided input to optimize the desired parameters and provide an optimal marketing mix solution through the output layer 24. . Apart from providing optimization results and associated metadata, the output layer 24 also provides real-time tracking of the algorithm's progress.

  The system 10 also includes a display module 26 for displaying user-provided inputs relating to marketing, evaluation criteria required from analysis of marketing data, and marketing mix solutions. In addition, the system 10 can include various software and hardware for formulating problem descriptions. For example, the system 10 includes a file server, application server, web server, disk server, database server, transaction server, telnet server, proxy server, list server, groupware server, file transfer protocol (FTP) server, audio / video server. LAN servers, DNS servers, firewalls, and the like.

  FIG. 2 shows an exemplary pre-modeling screen 30 of the system 10 of FIG. Screen 30 provides a user interface for classifying marketing mix variables. System 10 provides protected access for a user by authenticating the unique user name and corresponding password assigned to each user of system 10. In the illustrated embodiment, marketing data having multiple marketing mix variables can be uploaded into the system either manually or by uploading in a file having a specified format. A separate user interface (not shown) can also be used for access control and for uploading marketing data to the system 10.

  As is apparent from the figure, a plurality of marketing mix variables as displayed in cell 32 are assigned to a marketing mix category as displayed in cell 34. In this embodiment, the marketing mix variables include variables such as the number of newspaper advertisements per store, the number of coupons per store, the number of Google search impressions per store, and the television viewing rate (TRP) per store. Further, the marketing mix category includes business type, external, and the like. Variables can be further subdivided into specific marketing mix categories such as, among others, macroeconomic categories, promotional categories, media related categories, seasonal categories. The marketing mix variable is separated from the baseline variable and the periodicity for the time variable as shown in column 36 is specified. Note that users of system 10 can dynamically create and update marketing mix categories.

  FIG. 3 shows another exemplary pre-modeling screen 40 of the user interface of the system 10. User interface 40 is accessed by the user to perform EDA with marketing data. In this exemplary embodiment, selecting a variable from cell 42 and selecting a category from the marketing categories listed in cell 44 may generate a plot such as the conditional histogram shown in cell 46. it can. In one embodiment, a univariate plot of continuous variables is generated. The application uses the Sturges formula to determine the bin size for the data range in univariate analysis. In certain other embodiments, bivariate and correlation plots are generated for the selected data set. In another embodiment, a time series display at different time periods for multiple variables at a time can be obtained. In some other embodiments, factor analysis is used to group similar variables in the data set. Screen 40 also includes additional functions such as generating summary statistics for variables, selecting aggregate functions, and the like.

  FIG. 4 illustrates an exemplary screen 50 for creating a marketing mix variable, such as an adstock variable, using the system of FIG. In the illustrated embodiment, the variable is selected from cell 52 and a category is selected from the categories listed in cell 54. In addition, parameters such as attenuation rate and adstock variable name are provided in cell 56 to create an adstock variable. Here, as shown in cell 58, the user will be able to obtain a plot of the transformed and actual values of the variable. In this embodiment, the media data and promotion data are transformed using the Broadbent model by taking into account carry-over rates from previous promotion efforts. In certain other embodiments, new variables can be created through arithmetic transformations, lag-lead transformations and moving average transformations.

  FIG. 5 shows an exemplary modeling screen 60 of the system 10. In the illustrated embodiment, an appropriate modeling method can be selected depending on the type of marketing data to generate a model based on sales / revenue. In one embodiment, an existing model can be imported using the import option, as represented by reference numeral 62. As shown, a summary of the model output is given to the user (shown in cells 64 and 66) along with estimated statistical parameters such as R-square, MAPE, F statistics, Durbin-Watson statistics, variable coefficients, etc. . In one embodiment, modeled parameter fit values and actual values. In another embodiment, the residual can be plotted as a scatter plot. Alternatively, other plots / statistics can be generated to evaluate the model.

  FIG. 6 shows an exemplary analysis output screen 70 generated by the analysis module 20 of the system 10 of FIG. The analysis output screen 70 can display parameters such as the total contribution of marketing to sales, the individual contribution of each marketing channel to sales, and the return on investment (ROI) for each channel. In the illustrated embodiment, individual contributions for each contribution marketing mix variable are shown in plot 72. In addition, contribution and expenditure data for marketing mix variables for the previous time frame and the current time frame are shown in cells 74 and 76, respectively.

  In another exemplary embodiment, as shown in FIG. 7, a graphical display 80 of return on investment (ROI) for previous and current time frames for various marketing mix variables is generated. The As illustrated, the ROI for different time frames is represented by reference numbers 82 and 84. Conveniently, based on such data, marketing strategies can be adjusted to optimize spending by increasing the budget on the better ROI channel to improve revenue.

  FIG. 8 shows another exemplary simulation output screen 90 generated by the analysis module 20 of the system 10 of FIG. In the illustrated embodiment, a simulation is performed to predict sales and / or revenue for one or more products based on a marketing mix solution. In the illustrated embodiment, marketing spend for the current scenario is graphed by graph 92. In addition, expenditures corresponding to various marketing mix variables are represented by graph 94. Simulation results obtained by changing variables such as media variables and macroeconomic variables are represented in cell 96. Thus, the effect of changing the activity in the marketing segment can be observed using the simulation result. In addition, by executing various spending scenarios, marketing activities that can increase overall sales can be easily identified.

  The exemplary methods and systems described above enable a marketing mix solution to be generated based on various factors such as macroeconomic conditions, marketing channels, market conditions, and the like. Specifically, according to the present technique, pre-modeling marketing data having various marketing mix variables associated with a marketing strategy for one or more products to generate a response model based on sales and / or revenue. Thus, it becomes possible to identify contributing marketing mix variables that affect the sales and / or revenue of one or more products. The technique facilitates the correlation between sales history trends and marketing spending, as well as non-marketing factors, to identify factors that drive product sales.

  The technique further facilitates modeling effects of multiple factors, including media factors, promotional factors and macroeconomic factors, as well as the separation effect of each campaign in multi-channel marketing, to assess ROI and marginal revenue by marketing activity. To. The methods and systems discussed herein may form a marketing strategy for a product in the market by estimating the marketing effectiveness of current marketing activities and simulating future marketing scenarios, or existing Utilize efficient, robust, and reliable techniques to coordinate your marketing strategy.

  The proposed system uses a marketing planning process to facilitate analysis integration and to facilitate spend allocation and ROI optimization for various marketing channels. The system can accurately detect and respond instantly to market changes, creating customized marketing solutions on the base platform and adapting to the business needs to be deployed.

  FIG. 9 is a block diagram illustrating an example computing device 100 configured to generate a marketing mix solution according to this disclosure. In a very basic configuration 102, the computing device 100 typically includes one or more processors 104 and system memory 106. A memory bus 108 can be used for communication between the processor 104 and the system memory 106.

  According to the desired configuration, the processor 104 may be of any type including, but not limited to, a microprocessor (μP), a microcontroller (μC), a digital signal processor (DSP), or any combination thereof. Can do. The processor 104 may include one or more caching levels, such as a level 1 cache 110 and a level 2 cache 112, a processor core 114, and a register 116. The exemplary processor core 114 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP Core), or any combination thereof. The exemplary memory controller 118 can be used with the processor 104, or in some implementations the memory controller 118 can be an integral part of the processor 104.

  According to the desired configuration, the system memory 106 can be of any type including, but not limited to, volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. Can do. The system memory 106 can include an operating system 120, one or more applications 122, and program data 124. Application 122 may include a marketing mix analysis algorithm 126 that performs functions as described herein, including the functions described in connection with system 10 of FIG. Configured to do. Program data 124 may include input marketing data 128 and analysis parameters, as described herein. In some embodiments, the application 122 can be configured to operate with the program data 124 on the operating system 120 so that it can perform analysis of market data and generation of a marketing mix solution. This basic configuration 102 is shown in FIG. 9 by the components within the inner dashed line.

  The computing device 100 may have additional features or functions, as well as additional interfaces to facilitate communication between the base configuration 102 and any required devices and interfaces. For example, the bus / interface controller 130 can be used to facilitate communication between the base configuration 102 and one or more data storage devices 132 via the storage interface bus 134. The data storage device 132 can be a removable storage device 136, a non-removable storage device 138, or a combination thereof.

  Examples of removable and non-removable storage devices include magnetic disk drives such as flexible disk drives and hard disk drives (HDD), compact disk (CD) drives or digital versatile disk (DVD) drives, to name a few. Optical disk drives, solid state drives (SSD) and tape drives. Exemplary computer storage media are volatile and non-volatile, removable and non-removable media implemented in any method or technique for storing information such as computer readable instructions, data structures, program modules or other data. Can be included.

  System memory 106, removable storage device 136, and non-removable storage device 138 are examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage device, magnetic cassette, magnetic tape, magnetic disk storage It includes an apparatus or other magnetic storage device, or any other medium that can be used to store desired information and that can be accessed by computing device 100. Any such computer storage media may be part of computing device 100.

  The computer device 100 also has an interface for facilitating communication from various interface devices (for example, the output device 142, the peripheral device interface 144, and the communication device 146) to the basic configuration 102 via the bus / interface controller 130. A bus 140 may also be included. The exemplary output device 142 includes a graphics processing unit 148 and an audio processing unit 150 that can be connected to various external displays such as displays or speakers via one or more A / V ports 152. It can be configured to communicate.

  The exemplary peripheral interface 144 includes a serial interface controller 154 or a parallel interface controller 156, which are input devices (eg, keyboard, mouse, pen, voice, etc.) via one or more I / O ports 658. It can be configured to communicate with external devices such as input devices, touch input devices, etc.) or other peripheral devices (eg, printers, scanners, etc.). The exemplary communication device 146 includes a network controller 160 that facilitates communication with one or more other computer devices 162 over a network communication link via one or more communication ports 164. Can be configured to.

  A network communication link may be an example of a communication medium. Communication media typically can be embodied by computer readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and may include any information delivery media. it can. A “modulated data signal” can be a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and acoustic, radio frequency (RF), microwave, infrared (IR) and other wireless media. A wireless medium may be included. As used herein, the term computer readable media may include both storage media and communication media.

  Computer device 100 may be a mobile phone, personal digital assistant (PDA), personal media player device, wireless webwatch device, personal handset device, application specific device, or a hybrid device that includes any of the functions described above. It can be implemented as part of a small form factor portable (or mobile) electronic device. Computer device 100 can also be implemented as a personal computer including laptop and non-laptop computer configurations.

  As will be appreciated by those skilled in the art, the previous examples, illustrations and process steps can be implemented by suitable code on a processor-based system. It should also be noted that various embodiments of the present technique may perform some or all of the steps described herein in a different order or generally simultaneously, i.e. in parallel. Furthermore, these functions can be implemented in various programming languages such as C ++ or JAVA. As will be appreciated by those skilled in the art, such code can be one or more tangible machine-readable media, such as a memory chip, a local or remote hard disk, an optical disk (ie, CD or DVD) or other medium. Or can be configured to store, and the medium can be accessed by a processor-based system to execute stored code.

  The present disclosure should not be limited with respect to the specific embodiments described in this application, which are intended to illustrate various aspects. Many modifications and variations can be made without departing from the spirit and scope of the invention, as will be apparent to those skilled in the art. In addition to the methods and apparatus listed herein, functionally equivalent methods and apparatuses within the scope of the present disclosure will be apparent to those skilled in the art from the foregoing description. Such modifications and variations are intended to fall within the scope of the appended claims. The present disclosure should be limited only by such claims, along with the full scope of equivalents to which such claims are entitled. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

  With respect to the use of substantially any plural and / or singular terms herein, one of ordinary skill in the art can interpret them as singular and / or plural, as appropriate to the context and / or application. For clarity, the various singular / plurality may be specified herein.

  In general, terms used herein, and particularly in the appended claims (eg, the body of the appended claims), are intended to be generically intended as “unrestricted” terms. As will be understood by those skilled in the art (eg, the term “including” should be interpreted as “including but not limited to”), and the term “having” is “at least And the term “including” should be interpreted as “including but not limited to” etc.). Where a specific number of claim enumerations are intended to be introduced, such intent will be explicitly recited in the claims, and in the absence of such enumeration such enumeration One skilled in the art will further appreciate that there is no intent.

  For example, as an aid to understanding, the following appended claims may include use of the preface phrases “at least one” and “one or more” to introduce claim recitations. However, when using such a wording, an expression that does not specify a quantity, even if the same claim includes the prefaced wording “one or more” or “at least one” and an expression that does not specify a quantity. The introduction of claim enumeration by is to be construed to mean that any particular claim, including such introduced claim enumeration, is limited to embodiments that include only one such enumeration. Should not (eg, an expression that does not specify a quantity should be taken to mean "at least one" or "one or more"). The same is true for the use of expressions that do not specify the quantity used to introduce claim enumeration. Further, even if a specific number of introduced claim enumerations are explicitly recited, such enumeration should be construed to mean “at least the recited number”. Those skilled in the art will appreciate (eg, the as-is enumeration of “two enumerations” without other modifiers means at least two enumerations, or two or more enumerations).

While only certain features of the invention have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. Therefore, it is to be understood that the appended claims are intended to cover all such changes and modifications as fall within the true spirit of the invention.

Claims (20)

Each of the plurality of marketing mix variables is associated with a marketing strategy for one or more products, and pre-modeling marketing data having the plurality of marketing variables;
Generating a response model based on the sales and / or revenue to identify contributing marketing mix variables that affect sales and / or revenue of the one or more products; and
Analyzing the response model to determine an individual contribution of each of the contributing marketing mix variables to the sales and / or revenue of the one or more products.
A computer-implemented method for generating a marketing mix solution. Pre-modeling marketing data
Assigning one or more marketing categories to each of the plurality of marketing mix variables; and
Analyzing the plurality of marketing mix variables by performing exploratory data analysis (EDA);
A method for generating a marketing mix solution according to claim 1. The exploratory data analysis includes univariate analysis, or bivariate analysis, or time series analysis or factor analysis.
A method for generating a marketing mix solution according to claim 2. Generating a model based on sales and / or revenue includes transforming and / or adding one or more marketing mix variables to the model;
A method for generating a marketing mix solution according to claim 1. The one or more marketing mix variables include adstock variables, event variables, lead variables, lag variables, and combinations thereof.
A method for generating a marketing mix solution according to claim 4. The response model is generated using a linear regression model, a nonlinear regression model, or a mixed model.
A method for generating a marketing mix solution according to claim 4. Analyzing the response model further comprises comparing spending for each individual contribution of each of the contribution marketing mix variables.
A method for generating a marketing mix solution according to claim 1. Analyzing the response model further includes identifying each individual contribution of each of the contribution marketing mix variables to changes in sales over a predetermined period of time.
A method for generating a marketing mix solution according to claim 1. Analyzing the response model further includes comparing return on investment (ROI) for each of the contributing marketing mix variables.
A method for generating a marketing mix solution according to claim 1. Identifying one or more marketing strategies that contribute to the overall sales and / or revenue of the one or more products; and
Adjusting spending on the identified marketing strategy to generate the marketing mix solution,
A method for generating a marketing mix solution according to claim 1. Further predicting the sales and / or revenue of the one or more products based on the marketing mix solution;
A method for generating a marketing mix solution according to claim 9. A user interface for providing marketing data associated with a marketing strategy for one or more products;
A memory circuit configured to store the marketing data;
A processor configured to access the memory circuit, wherein the processor pre-models the marketing data to pre-model the marketing data and using a response model based on sales and / or revenue Is configured to identify contribution marketing mix variables that affect the sales and / or revenue of the one or more products,
A system for generating marketing solutions. The processor generates the pre-modeled marketing data by assigning a plurality of marketing mix variables to one or more marketing mix categories and analyzing the marketing mix variables using exploratory data analysis. Comprising an application module configured as
The system of claim 12. The marketing mix categories include macroeconomics, sales promotions, media related, seasons and combinations thereof.
The system of claim 13. The processor comprises an analysis module configured to analyze the response model to identify each individual contribution of the contributing marketing mix variable to the sales and / or revenue of the one or more products. ,
The system of claim 12. The analysis module is configured to generate a marketing mix solution based at least on the individual contributions of each of the contributing marketing mix variables.
The system according to claim 15. The analysis module is configured to determine a contribution rate for each marketing strategy, an estimated spending for each of the marketing strategies, and an estimated schedule for introducing the marketing strategies into the market.
The system of claim 12. The processor further comprises an optimization module configured to generate an optimal marketing mix solution based on the identified contributing marketing mix variable.
The system of claim 12. Each of the plurality of marketing mix variables is associated with a marketing strategy for one or more products, and pre-modeling marketing data having the plurality of marketing variables;
Generating a response model based on the sales and / or revenue to identify contributing marketing mix variables that affect the sales and / or revenue of the one or more products;
Analyzing the response model to determine an individual contribution of each of the contributing marketing mix variables to the sales and / or revenue of the one or more products;
Adjusting one or more marketing strategies in response to each individual contribution of each of the contributing marketing mix variables.
A computer-implemented method for generating a marketing mix solution. Analyzing the plurality of marketing mix variables by performing exploratory data analysis (EDA);
20. A method for generating a marketing mix solution according to claim 19.